hermes-feishu-streaming-card

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The workflow handles streaming messages, chat interactions, and webhook events from Feishu/Lark, which can contain outsider-submitted messages and interactive payloads.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs downloading and installing a third-party project release package directly via HTTP from a personal GitHub repository (https://github.com/baileyh8/...), which constitutes an unverifiable external runtime dependency with unofficial publisher provenance.